Deep Scattering Spectra with Deep Neural Networks for Acoustic Scene Classification Tasks

被引：0
|
作者：
ZHANG Pengyuan [1 ,2 ]
CHEN Hangting [1 ,2 ]
BAI Haichuan [1 ,2 ]
YUAN Qingsheng [3 ]
机构：
[1] Key Laboratory of Speech Acoustics and Content Understanding, Institute of Acoustics, Chinese Academy of Sciences
[2] University of Chinese Academy of Sciences
[3] National Computer Network Emergency Response Technical Team/Coordination Center of China
来源：
Chinese Journal of Electronics | 2019年 / 28卷 / 06期
关键词：
Acoustic scene classification; Time-delay neural network; Deep scattering spectrum; Detection and classification of acoustic scenes and events(DCASE);
D O I：
暂无
中图分类号：
TB52 [声学测量]; O657.3 [光化学分析法（光谱分析法）]; TP183 [人工神经网络与计算];
学科分类号：
070302 ; 0804 ; 081104 ; 0812 ; 081704 ; 0835 ; 1405 ;
摘要：
As one of the most commonly used features, Mel-frequency cepstral coefficients(MFCCs) are less discriminative at high frequency. A novel technique,known as Deep scattering spectrum(DSS), addresses this issue and looks to preserve greater details. DSS feature has shown promise both on classification and recognition tasks. In this paper, we extend the use of DSS feature for acoustic scene classification task. Results on Detection and classification of acoustic scenes and events(DCASE) 2016 and 2017 show that DSS provided 4.8% and 17.4% relative improvements in accuracy over MFCC features, within a state-of-the-art time delay neural network framework.
引用
收藏
页码：1177 / 1183
页数：7
相关论文
共 50 条
  • [41] A Fusion of Deep Convolutional Generative Adversarial Networks and Sequence to Sequence Autoencoders for Acoustic Scene Classification
    Amiriparian, Shahin
    Freitag, Michael
    Cummins, Nicholas
    Gerczuk, Maurice
    Pugachevskiy, Sergey
    Schuller, Bjoern
    [J]. 2018 26TH EUROPEAN SIGNAL PROCESSING CONFERENCE (EUSIPCO), 2018, : 977 - 981
  • [42] Deep Semantic Segmentation Neural Networks of Railway Scene
    He, Zhengwei
    Tang, Peng
    Jin, Weidong
    Hu, Chao
    Li, Wei
    [J]. 2018 37TH CHINESE CONTROL CONFERENCE (CCC), 2018, : 9095 - 9100
  • [43] MULTIFRAME DEEP NEURAL NETWORKS FOR ACOUSTIC MODELING
    Vanhoucke, Vincent
    Devin, Matthieu
    Heigold, Georg
    [J]. 2013 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2013, : 7582 - 7585
  • [44] On Vectorization of Deep Convolutional Neural Networks for Vision Tasks
    Ren, Jimmy S. J.
    Xu, Li
    [J]. PROCEEDINGS OF THE TWENTY-NINTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, 2015, : 1840 - 1846
  • [45] Late fusion framework for Acoustic Scene Classification using LPCC, SCMC, and log-Mel band energies with Deep Neural Networks
    Paseddula, Chandrasekhar
    Gangashetty, Suryakanth, V
    [J]. APPLIED ACOUSTICS, 2021, 172
  • [46] An Approach of Transferring Pre-trained Deep Convolutional Neural Networks for Aerial Scene Classification
    Devi, Nilakshi
    Borah, Bhogeswar
    [J]. PATTERN RECOGNITION AND MACHINE INTELLIGENCE, PREMI 2019, PT I, 2019, 11941 : 551 - 558
  • [47] Efficient design of neural networks for the classification of acoustic spectra
    Paul, Vlad S.
    Nelson, Philip A.
    [J]. JASA EXPRESS LETTERS, 2023, 3 (09):
  • [48] Automatic facies classification from acoustic image logs using deep neural networks
    You, Nan
    Li, Elita
    Cheng, Arthur
    [J]. INTERPRETATION-A JOURNAL OF SUBSURFACE CHARACTERIZATION, 2023, 11 (02): : T441 - T456
  • [49] Classification of Acoustic Physiological Signals Based on Deep Learning Neural Networks with Augmented Features
    Yang, Te-chung Issac
    Hsieh, Haowei
    [J]. 2016 COMPUTING IN CARDIOLOGY CONFERENCE (CINC), VOL 43, 2016, 43 : 569 - 572
  • [50] Android applications classification with deep neural networks
    Mustapha Adamu Mohammed
    Michael Asante
    Seth Alornyo
    Bernard Obo Essah
    [J]. Iran Journal of Computer Science, 2023, 6 (3) : 221 - 232
12345